llm-anthropic 0.31 adds support for Anthropic's new Fable 5.2 and Mythos 5.2 models
Original title: llm-anthropic 0.31
Anthropic released Fable 5.2 and Mythos 5.2, with Fable 5.2 currently ranked first on Artificial Analysis and priced at $8/million input and $40/million output, a 20% discount from Fable 5.1 ($10/$50). The author added the new models to llm-anthropic 0.31 and tested pelican-generation across all five reasoning levels, finding that max effort runs out of tokens after 128,000 thinking tokens and returns no image, a bug previously seen with Opus 5.5 but new to the Fable series.
Why it mattersThe author tested all five reasoning levels hands-on and flagged a max-effort bug that burns 128k thinking tokens without returning an image, useful for model selection.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.
Original article
Anthropic released Fable 5.2 and Mythos 5.2 today. Fable 5.2 is currently ranked first on Artificial Analysis. Anthropic say it "solved two open problems in the physics of black holes", so clearly their internal benchmarks have become more ambitious!
I've added the new models to llm-anthropic, so you can now run prompts through Fable 5.2 like this:
uv tool install llm
llm install llm-anthropic
llm keys set anthropic
# paste key here
llm -m claude-fable-5.2 "Generate an SVG of a pelican riding a bicycle"
I ran pelicans at all five reasoning levels - low, medium, high, xhigh, and max. You can see them all here - here's the best result I got, from xhigh:
max failed to return an image at all, running out of tokens after spending 128,000 thinking about them. That's the same bug that I saw with Opus 5.5 - but it's new for the Fable series, both Fable 5 and Fable 5.1 returned max effort pelicans just fine.
It's priced at $8/million input and $40/million output, which is a 20% discount on the previous Fable 5.1 ($10/$50).
I also used Fable 5.2 to help identify the source of a mysterious beep.
The original belongs to Simon Willison and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.
Studio